Platform

Products

Private AI infrastructure — from compute to agents.

Compute

GPU Instances
Dedicated GPUs, billed hourly
BYOK & Managed Keys
OpenAI, Anthropic, custom

Intelligence

Agents & Smart Routing
Virtual models, cost control
Fine-Tuning (LoRA)
Your data, your models
Knowledge Bases & RAG
Documents, vector search
Semantic Cache
Lower costs with AI caching

Integration

MCP Tools
Tools, APIs, external services
API Gateway
OpenAI-compatible endpoint
Data sovereignty
On-prem, EU hosting, GDPR

Target groups

Use Cases

For enterprise, SMBs, and individual developers.

Developers & Individuals

OpenClaw / OpenCode
Private and on-prem agents
MCP Integration
Tools directly in model context
OpenAI compatibility
Drop-in replacement, no SDK switch

SMB

Quick start with managed keys
No GPU required, start immediately
Your own assistants
Chatbot with RAG + system prompt
Fine-tuning with domain knowledge
Small model, precise answers

Enterprise

Compliance & Privacy
GDPR, no US cloud provider
Team rollout
Workspace, roles, API gateway
Cost Control
Smart routing reduces token costs

Knowledge & Support

Resources

Everything you need to succeed with Mycelis.

Learn

Getting Started
Productive in 5 minutes
Documentation
API reference & guides
Recipes
Copy-Paste Workflows

Community & Updates

Blog
News, guides & deep dives
Changelog
What is new in Mycelis?

Support

Status
Uptime & incidents
Contact
hello@mycelis.ai

Developers & Private

Your agents in
every coding tool.

Connect opencode, Cursor, Continue, or any OpenAI-compatible IDE extension to your own agents and models hosted on Mycelis — with a single config change.

Get Started Free Getting Started

Why use Mycelis for coding agents?

AI coding tools expect an OpenAI-compatible endpoint. Mycelis provides exactly that — with the added power of your own agents, fine-tuned models, and knowledge bases sitting behind the gateway. You keep full control over which model is used, what context it has, and what it can access.

What you get

Dedicated Inference

Run your models on dedicated GPU instances — no cold starts, no rate limits shared with others.

Custom Agents as Models

Each agent appears as a named model in your coding tool. Switch between agents by changing the model name.

MCP Tool Access

Give your coding agent access to MCP tools — docs search, issue trackers, or internal APIs — without configuring them in every tool separately.

API Key Management

Use a single Mycelis API key across all your tools. Revoke or rotate without touching your IDE configs.

Example: opencode.json

opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "provider": {
    "mycelis": {
      "npm": "@ai-sdk/openai-compatible",
      "options": { "baseURL": "https://app.mycelis.ai/api/proxy/v1" },
      "models": {
        "my-agent": { "name": "my-agent" }
      }
    }
  }
}

Point any OpenAI-compatible tool at your Mycelis agent by changing the base URL and model name.

Frequently Asked Questions

Which coding tools are supported?

Any tool that supports a custom OpenAI-compatible endpoint works — including opencode, Cursor, Continue, Aider, and many others. If it lets you set a base URL, it works with Mycelis.

Do I need to change my IDE setup for every agent?

No. You configure the Mycelis gateway once and select different agents by model name. No reconfiguration of your IDE is needed when you add or update agents.

Can I use fine-tuned models with coding tools?

Yes. Any model deployed on Mycelis — including fine-tuned ones — can be exposed as an agent and used directly in your coding tool.

Ready to supercharge your coding workflow?

Create a free account and connect your first agent to your IDE in minutes.

Get Started Free